程序猿最近要摘取pdf文件中的信息,选材用到了itextpdf工具包,整体比较简单,记录一下
1.pdf操作pom设置
<!-- https://mvnrepository.com/artifact/com.itextpdf/itextpdf -->
<dependency>
<groupId>com.itextpdf</groupId>
<artifactId>itextpdf</artifactId>
<version>5.5.13</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.itextpdf/itext-asian -->
<!-- 处理中文字符 -->
<dependency>
<groupId>com.itextpdf</groupId>
<artifactId>itext-asian</artifactId>
<version>5.2.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.bouncycastle/bcprov-jdk15 -->
<!-- 设置pdf查看密码使用 -->
<!-- <dependency> 这个没用
<groupId>org.bouncycastle</groupId>
<artifactId>bcprov-jdk15</artifactId>
<version>1.46</version>
</dependency> -->
<!-- https://mvnrepository.com/artifact/org.bouncycastle/bcprov-jdk15on -->
<dependency>
<groupId>org.bouncycastle</groupId>
<artifactId>bcprov-jdk15on</artifactId>
<version>1.62</version>
</dependency>
2.pdf文件的创建、属性标注
package com.chl.tools;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.itextpdf.text.BaseColor;
import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Font;
import com.itextpdf.text.PageSize;
import com.itextpdf.text.Paragraph;
import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.text.pdf.parser.PdfTextExtractor;
public class PdfParse {
private static Logger logger = LoggerFactory.getLogger(PdfParse.class);
private static String pdfPath = "/Users/chenhailong/Desktop/hellopdf.pdf";
public static void main(String[] args) {
createPdf();
}
/**
* 创建pdf文件
* 1.创建Document文档
* - 设置doc的多种属性
* 2.PdfWriter初始化
* 3.打开文档
* 4.写入内容
* 5.关闭文档
*
* 添加 itext-asian.jar 处理 中文问题
*/
private static void createPdf() {
try {
//设置pdf的纸张大小、背景色
Rectangle rect = new Rectangle(PageSize.A4.rotate());
rect.setBackgroundColor(BaseColor.WHITE);
//设置doc属性
Document document = new Document(rect);
document.addAuthor("作者");
document.addCreator("创作者");
document.addCreationDate();
document.addKeywords("pdf");
document.addSubject("主题");
document.addTitle("标题");
document.setMargins(10, 20, 30, 40);
PdfWriter pw = PdfWriter.getInstance(document, new FileOutputStream(pdfPath));
document.open();
document.add(new Paragraph("Hello World wh"));
//设置新的一页
document.newPage();
pw.setPageEmpty(false);
document.newPage();
document.add(new Paragraph("New page"));
document.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (DocumentException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
3.设置阅读密码
//设置阅读密码
//userPassword the user password. Can be null or empty
//ownerPassword the owner password. Can be null or empty
pw.setEncryption("123456".getBytes(), "123456".getBytes(),PdfWriter.ALLOW_SCREENREADERS,PdfWriter.STANDARD_ENCRYPTION_128);
如果包引入的不对,可能会引发以下的异常
Exception in thread "main" java.lang.NoClassDefFoundError: org/bouncycastle/asn1/ASN1Primitive
at com.itextpdf.text.pdf.PdfEncryption.<init>(PdfEncryption.java:147)
at com.itextpdf.text.pdf.PdfWriter.setEncryption(PdfWriter.java:2132)
at com.chl.tools.PdfParse.createPdf(PdfParse.java:59)
at com.chl.tools.PdfParse.main(PdfParse.java:27)
Caused by: java.lang.ClassNotFoundException: org.bouncycastle.asn1.ASN1Primitive
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:349)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 4 more
或
Exception in thread "main" java.lang.SecurityException: class "org.bouncycastle.asn1.ASN1Primitive"'s signer information does not match signer information of other classes in the same package
at java.lang.ClassLoader.checkCerts(ClassLoader.java:898)
at java.lang.ClassLoader.preDefineClass(ClassLoader.java:668)
at java.lang.ClassLoader.defineClass(ClassLoader.java:761)
at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
at java.net.URLClassLoader.defineClass(URLClassLoader.java:467)
at java.net.URLClassLoader.access$100(URLClassLoader.java:73)
at java.net.URLClassLoader$1.run(URLClassLoader.java:368)
at java.net.URLClassLoader$1.run(URLClassLoader.java:362)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:361)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:349)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at com.itextpdf.text.pdf.PdfEncryption.<init>(PdfEncryption.java:147)
at com.itextpdf.text.pdf.PdfWriter.setEncryption(PdfWriter.java:2132)
at com.chl.tools.PdfParse.createPdf(PdfParse.java:59)
at com.chl.tools.PdfParse.main(PdfParse.java:27)
4.设置pdf可以写入中文
//如有中文,需要设置font字体 , 依赖 itext-asian
BaseFont bfChinese = BaseFont.createFont( "STSongStd-Light" ,"UniGB-UCS2-H",BaseFont.NOT_EMBEDDED);
Font font = new Font(bfChinese);
document.add(new Paragraph("这是中文汉字",font));
5.读取pdf文件
//读取pdf文件的内容
private static void readPdf(String pdfPath) {
try {
pdfPath = "/Users/chenhailong/Desktop/中华人民共和国刑法修正案(九)全文.pdf";
PdfReader pdf = new PdfReader(pdfPath);
int i =pdf.getNumberOfPages();
for(int count = 1;count<=i;count++) {
System.out.println(PdfTextExtractor.getTextFromPage(pdf, count));
}
} catch (IOException e) {
logger.info("read failed!{}",e);
e.printStackTrace();
}
}
针对pdf的写入操作,包含很多设置,请参考官网
操作pdf有 itextpdf, apache poi等工具,各个之间的对比参考